Cosmos3-Nano LIBERO-10 policy checkpoint for synthetic-data robotics study released
AINVIDIA releases a Cosmos3-Nano action policy post-trained on LIBERO-10 with training seed 43, as a bf16 checkpoint of about 30 GB. The model scores 91.8 ± 0.5% on standard LIBERO-10 scenes and 86.8 ± 1.1% on perturbed scenes, which NVIDIA measured on its evaluation bed. The training data is not redistributed, and the checkpoint is governed by the NVIDIA Open Model License.
Source details
NVIDIA · new models on Hugging Face · huggingface.coPublished · added here
Original title: nvidia/cosmos3-nano-libero10-sdg-export-S5_2_s43